{"id":"https://openalex.org/W164679808","doi":"https://doi.org/10.21437/eurospeech.2001-162","title":"Auditory model based speech recognition in noisy environment","display_name":"Auditory model based speech recognition in noisy environment","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W164679808","doi":"https://doi.org/10.21437/eurospeech.2001-162","mag":"164679808"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-162","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078872209","display_name":"Xiaoqing Yu","orcid":"https://orcid.org/0000-0003-4585-9372"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaoqing Yu","raw_affiliation_strings":["The Hong Kong Polytechnic University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University#TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026951061","display_name":"Wanggen Wan","orcid":"https://orcid.org/0000-0002-5065-9650"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wanggen Wan","raw_affiliation_strings":["The Hong Kong Polytechnic University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University#TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045479823","display_name":"Daniel Pak-Kong Lun","orcid":"https://orcid.org/0000-0003-3891-1363"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Daniel P. K. Lun","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"611","last_page":"614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.838876485824585},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8135037422180176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7543990612030029},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5976220965385437},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5228217840194702},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4921419024467468},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.43592238426208496},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4354201555252075},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43380507826805115},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43316149711608887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43010786175727844},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4200131297111511},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37581944465637207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11216476559638977}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.838876485824585},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8135037422180176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7543990612030029},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5976220965385437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5228217840194702},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4921419024467468},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.43592238426208496},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4354201555252075},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43380507826805115},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43316149711608887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43010786175727844},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4200131297111511},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37581944465637207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11216476559638977},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2001-162","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/46870","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/46870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W172350543","https://openalex.org/W1490847884","https://openalex.org/W2073693905","https://openalex.org/W2129382277","https://openalex.org/W2135034868","https://openalex.org/W2158483598","https://openalex.org/W2538749997"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2070163607","https://openalex.org/W2064537740"],"abstract_inverted_index":{"The":[0,35,154],"main":[1],"purpose":[2],"of":[3,38,87,90,104,113,130,195],"this":[4,70],"paper":[5],"is":[6,30,46,98,161,173,181],"to":[7,10,48,165],"present":[8],"how":[9],"raise":[11],"the":[12,21,32,65,78,84,121,126,128,133,159,178,186,193],"speech":[13,25,28,39,54,76,80,96,122],"recognition":[14,29,36,40,179],"performance":[15,129],"in":[16,27,52,60,64,137,175,192],"noisy":[17,61,67,141],"environment.":[18,68],"So":[19],"far":[20],"most":[22],"popularly":[23],"used":[24,174],"feature":[26,81,97],"probably":[31],"so-called":[33],"MFCC.":[34,168],"rate":[37,180],"algorithm":[41],"using":[42,100,144],"MFCC":[43,131,188],"and":[44,107,117,132,140,150],"CDHMM":[45,146],"known":[47],"be":[49],"very":[50],"high":[51],"clean":[53,139],"environment,":[55,62],"but":[56],"it":[57,118],"deteriorates":[58],"greatly":[59],"especially":[63],"white":[66,198],"In":[69,125],"paper,":[71],"we":[72],"propose":[73],"a":[74],"new":[75,95],"feature,":[77],"ASBF":[79,134,160,176],"based":[82],"on":[83],"mathematical":[85,102],"model":[86,103,112],"inner":[88,105],"ear":[89,106],"human":[91,114],"auditory":[92,109,115],"system.":[93],"This":[94],"extracted":[99],"both":[101,138],"primary":[108],"nerve":[110],"processing":[111],"system,":[116],"can":[119],"track":[120],"formants":[123],"effectively.":[124],"experiment,":[127],"are":[135],"compared":[136],"environments":[142],"when":[143],"left-to-right":[145],"with":[147,189,197],"6":[148],"states":[149],"5":[151,171],"Gaussian":[152],"mixtures.":[153],"experimental":[155],"result":[156],"shows":[157],"that":[158],"much":[162],"more":[163],"robust":[164],"noise":[166],"than":[167,185],"When":[169],"only":[170],"dimension":[172,191],"vector,":[177],"approximately":[182],"38.6%":[183],"higher":[184],"traditional":[187],"39":[190],"condition":[194],"S/N=10dB":[196],"noise.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}